Position Bias Mitigation: A Knowledge-Aware Graph Model for Emotion Cause Extraction
This addresses a dataset bias issue in ECE for NLP researchers, offering a more robust solution, though it is incremental as it builds on existing graph-based methods.
The paper tackles the problem of position bias in Emotion Cause Extraction (ECE) by proposing a knowledge-aware graph model that explicitly models emotion triggering paths using commonsense knowledge. The approach performs comparably to state-of-the-art methods on the original dataset and shows improved robustness against adversarial attacks, with a significant performance drop observed in existing models when tested on adversarial examples.
The Emotion Cause Extraction (ECE)} task aims to identify clauses which contain emotion-evoking information for a particular emotion expressed in text. We observe that a widely-used ECE dataset exhibits a bias that the majority of annotated cause clauses are either directly before their associated emotion clauses or are the emotion clauses themselves. Existing models for ECE tend to explore such relative position information and suffer from the dataset bias. To investigate the degree of reliance of existing ECE models on clause relative positions, we propose a novel strategy to generate adversarial examples in which the relative position information is no longer the indicative feature of cause clauses. We test the performance of existing models on such adversarial examples and observe a significant performance drop. To address the dataset bias, we propose a novel graph-based method to explicitly model the emotion triggering paths by leveraging the commonsense knowledge to enhance the semantic dependencies between a candidate clause and an emotion clause. Experimental results show that our proposed approach performs on par with the existing state-of-the-art methods on the original ECE dataset, and is more robust against adversarial attacks compared to existing models.